CN-121978114-A - Mura defect detection method and AOI defect detection equipment

CN121978114ACN 121978114 ACN121978114 ACN 121978114ACN-121978114-A

Abstract

The application relates to the technical field of defect detection of display screens, in particular to a Mura defect detection method and AOI defect detection equipment, wherein a substrate is positioned on a carrier; the method comprises the steps of obtaining a second image of an area of a substrate, wherein the area is located by a second target point, the second target point is a point which is obtained after a first target point moves along with the substrate on a carrying platform for a preset distance in the X-axis direction, the X-axis direction is the printing direction of an ink-jet printer, if the second image comprises the area to be detected, determining that the defect type of the area to be detected is a first defect type, and the first defect type comprises Mura defects. The method can improve the accuracy of Mura defect detection and reduce the problem of missing detection.

Inventors

CHENG ZHI
MA WEIFEI
TANG WEI
ZHANG LIJUN

Assignees

广东国创科光电装备有限公司

Dates

Publication Date: 20260505
Application Date: 20260211

Claims (10)

1. A method for detecting Mura defects, wherein a substrate is positioned on a stage, the method comprising: Acquiring a first image of an area to be detected on a substrate, wherein the area to be detected comprises a first target point; Acquiring a second image of an area of the substrate, wherein the area is located at a second target point, the second target point is a point which is obtained after the first target point moves along with the substrate on a carrying platform for a preset distance in the X-axis direction, and the X-axis direction is the printing direction of the ink-jet printer; and if the second image comprises the region to be detected, determining that the defect type of the region to be detected is a first defect type, wherein the first defect type comprises Mura defects.
2. The method of detection according to claim 1, wherein the method of detection further comprises: and if the second image does not comprise the region to be detected, determining that the defect type of the region to be detected is a second defect type, wherein the second defect type comprises one or two of a camera lens dirt defect and a carrier defect.
3. The inspection method of claim 1, wherein the first defect type further comprises a smudge defect at the bottom of the substrate, and wherein the inspection method further comprises determining a Mura defect area in the second image after determining that the defect type of the area to be inspected is the first defect type; Said determining the Mura defect area in the second image comprises: acquiring definition evaluation values of a plurality of areas in a second image, wherein the plurality of areas in the second image comprise a first area and a second area; Judging whether the definition evaluation value of the plurality of areas of the second image is larger than or equal to a preset definition evaluation threshold value; And if the definition evaluation value of the second area is smaller than the preset definition evaluation threshold, determining the second area as a dirty defect area at the bottom of the substrate.
4. The inspection method of claim 1, wherein the first defect type further comprises a smudge defect at the bottom of the substrate, and wherein the inspection method further comprises determining a Mura defect area in the second image after determining that the defect type of the area to be inspected is the first defect type; Said determining the Mura defect area in the second image comprises: Acquiring a third image of the area of the substrate, where the second target point is located, wherein the third image is a shot image when the focal plane of the camera is located on the lower surface of the substrate; acquiring definition evaluation values of a plurality of areas in a second image and definition evaluation values of a plurality of areas in a third image; Comparing the first definition evaluation value with a second definition evaluation value, wherein the first definition evaluation value is a definition evaluation value of a third area in the second image, the second definition evaluation value is a definition evaluation value of a fourth area in the third image, and the third area and the fourth area are the same area on the substrate; And if the first definition evaluation value is larger than the second definition evaluation value, determining the third area as a Mura defect area.
5. The method of detection of claim 4, further comprising: And if the first definition evaluation value is smaller than the second definition evaluation value, determining the fourth area as a dirty area at the bottom of the substrate.
6. The method according to any one of claims 3 to 5, wherein obtaining sharpness evaluation values of a plurality of areas in the second image specifically includes: acquiring a pixel point gray matrix of a first area in a second image, wherein the first area is any area in the second image; obtaining a definition evaluation value of a first region according to a preset mode, wherein the preset mode comprises the following steps: The pixel gray value of the x-th row and the y-th column.
7. The method of any one of claims 3-5, wherein the depth of field of the camera is less than the thickness of the substrate.
8. The method according to claim 1, wherein the first image and the second image are both captured images when a focal plane of the camera is located on an upper surface of the substrate.
9. The detection method according to claim 1, wherein the size of the area where the second target point is located is larger than or equal to the size of the area to be detected; And before acquiring the first image of the region to be detected on the substrate, the detection method comprises acquiring a plurality of regions to be detected on the substrate.
10. AOI defect detection device, characterized by comprising a processor, a memory for storing instructions, a user interface and a network interface, both for communicating with other devices, the processor being adapted to execute the instructions stored in the memory for causing the AOI defect detection device to perform a Mura defect detection method according to any one of claims 1-9.

Description

Mura defect detection method and AOI defect detection equipment Technical Field The application relates to the technical field of defect detection of display screens, in particular to a Mura defect detection method and AOI defect detection equipment. Background Currently, automatic optical inspection (Automatic Optic Inspection, AOI) refers to acquiring an image of a measured object by adopting an optical imaging technology (usually using a camera and a lens), and then acquiring information such as the size, the position, the direction, the spectral characteristics, the structure, the defects and the like of the object from the shot image through a certain image processing algorithm, so that tasks such as inspection of a display screen product can be performed. AOI defect detection equipment is widely applied to the defect detection field of display screens. However, AOI defect detection devices typically use deep learning vision algorithms to learn display panel (also referred to as substrate) defect samples, and all of the defect samples are known defects. On the one hand, new unknown defects appear successively, on the other hand, the substrate yield is higher, namely the number of defect samples is smaller, but the number of non-defect samples is larger, so that the problem of missed detection exists after deep learning, and especially the Mura defect of the display screen after ink-jet printing can be mixed with dirt (such as dust or particles) on a camera, an air floatation hole or a threaded hole on a carrier, dirt at the bottom of the substrate and the like. Therefore, for the problem of missing detection of Mura defects, a method for detecting Mura defects and an AOI defect detecting apparatus are needed. Disclosure of Invention The application provides a Mura defect detection method and AOI defect detection equipment, which can improve the accuracy of Mura defect detection and reduce the problem of missing detection. The first aspect of the application discloses a Mura defect detection method, wherein a substrate is located on a carrier, the detection method comprises the steps of obtaining a first image of a region to be detected on the substrate, wherein the region to be detected comprises a first target point, obtaining a second image of the region of the substrate, the region is located in a second target point, the second target point is obtained after the first target point moves along the substrate on the carrier for a preset distance in the X-axis direction, the X-axis direction is the printing direction of an ink-jet printer, and if the second image comprises the region to be detected, determining that the defect type of the region to be detected is a first defect type, and the first defect type comprises Mura defects. In the above scheme, the defect is determined to be the Mura defect by moving the target point along with the substrate into two images before and after the substrate, and the two images are in the same region of the substrate, if the two images both comprise the region to be detected, indicating that the region to be detected is on the substrate. The method has the advantages of high efficiency and high accuracy in identifying the Mura defect, and the problem of missed detection of the Mura defect can be avoided. Whether the second image includes the region to be detected or not can be judged by carrying out similarity calculation on the first image and the second image and confirming whether the region with similarity exists or not, or can be judged by carrying out difference result on the first image and the second image, and detailed description and limitation are omitted. In one possible implementation mode, the detection method further comprises determining that the defect type of the to-be-detected area is a second defect type if the second image does not include the to-be-detected area, wherein the second defect type comprises one or two of a camera lens dirt defect and a carrier defect. In the above-described embodiments, description is made of a case of a non-substrate defect. The second image does not comprise the area to be detected, and the defect is that on the carrier, the camera shoots the similar defect of an air floatation hole, a threaded hole and the like on the carrier and the similar defect of lens dirt, and the similar defect cannot move along with the movement of the substrate. In one possible implementation manner, the first defect type further comprises a dirty defect at the bottom of the substrate, the detection method further comprises the steps of determining a Mura defect area in the second image after determining that the defect type of the area to be detected is the first defect type, determining the Mura defect area in the second image comprises the steps of obtaining definition evaluation values of a plurality of areas in the second image, wherein the plurality of areas in the second image comprise a first area and a second area, judging wh